metadata
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: MAE Model (model_idx_0302)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | MAE |
| Split | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 302 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9679 |
| Val Accuracy | 0.7213 |
| Test Accuracy | 0.7176 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, plain, mushroom, porcupine, tractor, bus, bowl, crab, willow_tree, boy, raccoon, skyscraper, elephant, fox, kangaroo, streetcar, can, bee, skunk, worm, cup, rose, ray, rocket, butterfly, bed, bridge, whale, lizard, bicycle, mountain, pear, seal, hamster, house, wolf, chair, oak_tree, dinosaur, cockroach, sunflower, clock, man, turtle, cloud, castle, tank, baby, sweet_pepper, sea